Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.8728. Min Act: -0.0000

Data Index: 106731 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.7777. Min Act: -0.0000

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.6973. Min Act: -0.0000

Data Index: 296487 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.5562. Min Act: -0.0000

Data Index: 637869 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.8086. Min Act: -0.0000

Data Index: 630180 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.6540. Min Act: -0.0000

Data Index: 906060 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.7771. Min Act: -0.0000

Data Index: 530517 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.7059. Min Act: -0.0000

Data Index: 318523 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.5275. Min Act: -0.0000

Data Index: 117695 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.3329. Min Act: -0.0000

Data Index: 174024 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.3409. Min Act: -0.0000

Data Index: 100676 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.1766. Min Act: -0.0000

Data Index: 718673 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.2127. Min Act: -0.0000

Data Index: 199659 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1079480 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.0009. Min Act: -0.0000

Data Index: 307535 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.8728. Min Range: -2.8728

Max Act: 2.1236. Min Act: -0.0000

Data Index: 999609 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.8728. Min Range: -2.8728

Max Act: 1.9070. Min Act: -0.0000

Data Index: 1320238 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 2.8728. Min Range: -2.8728

Max Act: 1.9738. Min Act: -0.0000

Data Index: 872103 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 2.8728. Min Range: -2.8728

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 2.8728. Min Range: -2.8728

Max Act: 1.7393. Min Act: -0.0000

Data Index: 127670 (C4 (Web Text))

Max Activating Token Index: 604